Artifact-Bench (AI-Generated Video) - Artifact Identification: leaderboard
Metric: Accuracy (%) on the 350 multi-answer questions asking for every observable artifact type among six fine-grained candidates (AID), the unweighted mean of the three difficulty levels, 1,100 manually annotated questions on 1,350 real and AI-generated videos from seven generators, at 5 fps frame sampling, each model at its officially recommended decoding (Gemini 3.1 Pro at temperature 1.0 and high thinking level) or greedy, answers parsed by Gemini 3.1 Pro; higher is better. Source: arxiv.org. Saturation forecast: Around 2032. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 9.8 |
| 2 | Gemini 3 Flash | 9.8 |
| 3 | Qwen 3 VL 32B (Thinking) | 9.6 |
| 4 | Qwen 3 VL 30B A3B (Thinking) | 7.8 |
| 5 | Molmo2-8B | 7.8 |
| 6 | Qwen 3 VL 32B Instruct | 7.3 |
| 7 | Qwen 3 VL 30B A3B Instruct | 6.9 |
| 8 | Qwen 3 VL 8B (Thinking) | 5.9 |
| 9 | Qwen 3 VL 8B Instruct | 5.5 |
Interactive version: theaggregate.ai/benchmark?slug=artifact-bench-ai-generated-video-artifact-identification · How It Works · Data refreshed daily, snapshot 2026-10-07.